4735 results about "Image frame" patented technology

The present disclosure relates to the field of computer vision and discloses a three-dimensional dynamic scene reconstruction method and apparatus, and a storage medium. The three-dimensional dynamic scene reconstruction method comprises: acquiring synchronized videos of a plurality of viewpoints of a dynamic scene; computing matching points between video images of different viewpoints, and estimating intrinsic and extrinsic parameters of each camera; obtaining a Gaussian splatting point set {p0} on the basis of a sparse point cloud constructed according to the depth of each matching point; for the first image frame of each video, using {p0} to perform static training thereon, to obtain a Gaussian splatting point set {p}; for the remaining image frames, dividing {p} into a static point set {S} and a dynamic point set {D}, performing dynamic training on {D}, and constructing a dynamic Gaussian splatting point set {P} from {p}, {S}, and the final {D}; and, in view of the intrinsic and extrinsic parameters of each camera, rendering {P} using a Gaussian splatting rendering pipeline, to obtain rendered images at different moments from new viewpoints.

The invention discloses a light guide plate defect detection method and system based on a neural network, and particularly relates to the technical field of machine vision detection, and the method comprises the following steps: aiming at the problem of image instability of a light guide plate in a dynamic transmission or rotation process, continuously collecting an image sequence and extracting time domain features; and performing interference judgment in combination with the inter-frame consistency prediction coefficient and a first threshold to realize accurate identification of the abnormal image frame. For an abnormal image frame, further correcting the recognition credibility of the abnormal image frame by adopting a confidence adjustment and fusion mode, and meanwhile, introducing a frequency domain transformation and image enhancement strategy to compensate detail loss caused by motion blur; according to the method, inter-frame consistency analysis, confidence fusion regulation and control and frequency domain fuzzy recognition and compensation mechanisms are introduced, abnormal judgment and image quality restoration of the light guide plate image in the dynamic scene are realized, the recognition accuracy and stability of the neural network model on the defect type, position and confidence are improved, and the false detection and omission ratio is effectively reduced.

The invention relates to the technical field of image steady state adjustment, and provides a self-adaptive image stabilization and dynamic horizontal reference calibration method and device, equipment and a medium. Time domain alignment and motion parameter interpolation processing are carried out on original sensor data to obtain a synchronized motion parameter data stream, and multi-sensor data fusion filtering is carried out on the synchronized motion parameter data stream to obtain equipment three-dimensional attitude parameters. The method comprises the following steps: performing motion mapping on an original image frame according to equipment three-dimensional attitude parameters to obtain an image displacement compensation matrix, performing feature tracking and pixel resampling on the original image frame according to the image displacement compensation matrix to obtain a preliminary stable image set, and performing horizon detection and rotation compensation on the preliminary stable image set to obtain a horizontal reference alignment image set; and performing time sequence weighted fusion on the horizontal reference alignment image set to obtain a steady-state video data stream. Through multi-sensor fusion, high-precision mapping, image adaptive calibration and weighted fusion, the precision of motion jitter suppression and horizontal calibration is improved.

An action localization method, device, electronic equipment, and computer-readable storage medium are provided. The action localization method includes: identifying at least one target video segment containing a target object in a video; acquiring a first action recognition result of at least one image frame in the at least one target video segment and a second action recognition result of the target video segment; and acquiring an action localization result of the video based on the first action recognition result and the second action recognition result.

The invention relates to the field of image recognition, in particular to a wind power construction intelligent safety management method and system based on intelligent AI monitoring. The method comprises the following steps: obtaining an omnibearing real-time image flow of a wind power construction area, carrying out super-resolution deep convolution optimization and operator three-dimensional image segmentation, and extracting an operator three-dimensional image frame; three-dimensional point cloud modeling of the construction area is carried out based on the image flow, real-time image frame position positioning rendering is carried out according to a three-dimensional image frame, and a real-time twinborn model of the construction area is constructed; performing operation dynamic behavior analysis and behavior deviation degree quantitative analysis based on a twin model to obtain the behavior deviation degree of the operator; and according to the behavior deviation degree, carrying out early prediction analysis on illegal behaviors, making an adaptive risk early warning decision, and constructing an operation behavior risk early warning strategy. According to the invention, through real-time operation behavior identification and environmental risk analysis, the intelligence and safety level of wind power construction are improved.

The invention relates to the technical field of target detection, and discloses a pet target detection method and device and a camera, and the method comprises the steps: carrying out the motion triggering collection and image enhancement preprocessing of a front end region of a feeder, and obtaining an enhanced image frame sequence; performing feature extraction of dynamic receptive field adjustment on the enhanced image frame sequence to obtain pet feature descriptors and position information; behavior time sequence feature analysis is executed, and pet behavior sequence feature vectors are obtained; constructing a state transition diagram according to the pet behavior sequence feature vector, and performing time sequence consistency analysis to obtain a pet state judgment result; power management and decision execution are carried out on the feeder based on the pet state judgment result, feeding control under the low-power-consumption condition is achieved, behavior misjudgment caused by posture fluctuation is effectively avoided, the behavior recognition accuracy is improved, the accurate feeding control problem in a multi-pet family is solved, and the user experience is improved.

Disclosed in the present invention are an edge-deployed semi-supervised anomaly detection method and system for a railway track foreign object. The method comprises the following steps: an edge device encoding and decoding a video stream captured by a camera to obtain an image frame sequence, and performing frame extraction; and using a semantic segmentation model to perform image segmentation on a certain image frame obtained by means of frame extraction, to obtain a railway track region segmentation image. The use of a single image as input may generate an expert model result having a high weight value; however, the determination based on a single image is not stable, multiple consecutive images of the task scene need to be inputted, the frequency of each expert model obtaining the highest weight is computed, and the expert model corresponding to the highest frequency is the final solution. The present invention supports scene-adaptive foreign object detection algorithm automatic selection, and a user can perform selection on the basis of prior knowledge, or selection may be performed by a scene-adaptive automatic algorithm selection method; the user only needs to provide a batch of image data of the current scene, and the optimal algorithm selection can be evaluated.

The invention provides a hull surface defect detection system based on machine vision, and relates to the technical field of data processing. The image correction module is used for carrying out illumination equalization processing and geometric distortion correction; the region construction module is used for identifying a defect-free stable region and generating reference region data which comprises a brightness model and a texture model; the candidate generation module is used for detecting a region where texture interruption or abnormal bright spots exist locally to form candidate defect data, and the candidate defect data comprise pixel positions and local contrast parameters; the stability judgment module is used for carrying out projection matching in the multiple frames of images and simultaneously carrying out joint comparison with the brightness model and the texture model of the reference area data to form real defect data and false defect data; the result output module is used for generating a detection result containing defect coordinates, defect contours, image frame numbers and interference sample prompts; the accuracy of hull surface defect detection is improved.

The invention discloses an SPR response region identification method based on image semantic segmentation and time sequence alignment, and the method comprises the following steps: collecting SPR image frame sequence data, and constructing an original image sequence; performing image preprocessing operation on the original image sequence, and outputting a standardized image sequence; constructing a time sequence window image set composed of multiple continuous frames; inputting the time sequence window image set into an improved SegFormer model, and generating a response region segmentation mask image corresponding to each frame; executing cross-frame time sequence alignment operation of the response area, and outputting time sequence consistency identification mapping of the response area; performing area statistics, intensity analysis and time positioning operation; and generating a structured response region recognition result. The spatial-temporal evolution process of the response area in the SPR image sequence can be effectively recognized, the accuracy and stability of response area recognition are improved, and the method is suitable for high-precision biological detection and real-time molecular analysis scenes.

The invention discloses a short video network public opinion information identification method based on an image processing technology, and relates to the technical field of artificial intelligence and image processing, and the method comprises the following steps: S001, through obtaining image frames, audio tracks and time sequence information of a short video, constructing a multi-modal fusion model, extracting continuous image frames with suspicious identity features, and carrying out the recognition of the short video network public opinion information; generating a forgery risk area distribution map; and S002, performing semantic consistency verification according to the counterfeit risk region distribution map, and extracting space and time anomaly features existing among facial micro-expressions, pronunciation actions and background semantics in the image frame. According to the method, a multi-modal model is constructed by fusing image, audio and time information, fine abnormal features, traceability forgery starting points and propagation paths in a deep forgery video are identified, and an identification strategy and a public opinion response mechanism are dynamically adjusted, so that accurate identification, adaptive processing and closed-loop control of short video public opinion risks are realized; and the identification accuracy and the treatment efficiency are improved.

The invention discloses a traffic operation and maintenance fault intelligent scheduling method and system based on an AI large model, and belongs to the technical field of traffic control. The method comprises the following steps: collecting a vehicle driving track GPS coordinate set, a traffic flow density matrix, a vehicle-mounted camera monitoring image frame sequence and a fault vehicle owner speed anomaly detection result in real time; constructing a traffic operation state analysis model, and outputting real-time traffic operation state characteristics; generating a traffic fault probability distribution curved surface in a future time window; generating a comprehensive fault positioning confidence coefficient matrix; and planning an optimal maintenance resource path according to the pheromone updating rule, and updating the optimal maintenance resource path to the visual scheduling platform in real time. According to the method, space-time diagram convolutional network dynamic modeling is constructed according to multi-source data, so that the limitation of a space blind area of a single data source is broken through, the fault positioning speed is improved, and the problems of incomplete coverage and low positioning speed in the prior art are solved.

The invention discloses an unmanned aerial vehicle inspection method and system applied to foundation pit accumulated water monitoring, and the method comprises the steps: determining an optimal route node sequence, and generating an unmanned aerial vehicle control instruction set; acquiring internal and external parameters of a multi-source sensor, and performing time alignment compensation on image frames and sensor data; acquiring a ponding area image coordinate set and attribute data; a three-dimensional projection point set of the ponding area is obtained, and the real coverage area of the ponding area is calculated; generating a three-dimensional overview map of the foundation pit by using the multi-view image of the foundation pit area; determining a three-dimensional coordinate point set and an area estimation result of the ponding area; and projecting the three-dimensional coordinate point set of the ponding area to the three-dimensional overview map of the foundation pit to generate a hidden danger monitoring report. By integrating the unmanned aerial vehicle, the sensor data and the advanced image processing technology, the accuracy, stability and visualization effect of foundation pit accumulated water monitoring are greatly improved, more reliable and comprehensive technical support is provided for safety management of foundation pit engineering, and the safety risk in the construction process is remarkably reduced.

The invention discloses an aircraft target tracking method and system based on compensation prediction, which are used for improving the target tracking precision in an image transmission delay scene. The method comprises the following steps: firstly, acquiring an image frame sequence of a target aircraft by using an airborne monocular camera, extracting a target center coordinate through a small target detection algorithm, and constructing a position sequence; the method comprises the following steps: extracting current high-frequency I MU data aiming at the condition that an image frame has transmission delay, inputting the current high-frequency I MU data into an LSTM-DKF model constructed by fusing LSTM and a delay Kalman filter, and predicting and generating a process noise and observation noise covariance matrix; and initializing a delay Kalman filter by using the matrix, and recursively predicting the target position during the delay period. And when the delayed image frame is received, backtracking and updating the state of the filter, recurring to the current moment again, and outputting the compensated target position. And finally, pixel deviation is calculated according to the compensation position, an aircraft tracking control instruction is generated, and high-precision target tracking is realized.

The invention relates to the technical field of surface defect detection, in particular to a structure surface disease diagnosis method and system based on multi-modal edge calculation, and the method comprises the following steps: obtaining an infrared thermal image frame image and constructing a temperature difference image group, enhancing visible light texture features to generate an enhanced image group, carrying out image registration, extracting a combined feature vector, and carrying out classification and recognition. And mapping the boundary of the defect area to generate a coordinate set, counting disease information and generating a visual display layer. According to the method, thermal anomaly features in different areas can be visually expressed through temperature mapping and space division operation of the infrared thermal imaging image, accurate judgment of defect types is realized through a trained neural network model, a boundary coordinate point set of structure surface defects is extracted through an image mapping means, and the accuracy of the structure surface defects is improved. And in combination with connectivity operation and a rectangular frame construction mode, defect positions are labeled and positioned, so that the accuracy of building surface disease identification, the reliability of boundary extraction and the integrity of zoning risk presentation are effectively improved.

The invention relates to the technical field of model analysis, in particular to an imaging flow cytometry cell detection method based on an improved model. The method comprises the following steps: introducing a cell sample to be detected into an imaging flow cytometry system integrated with a micro-fluidic chip for continuous image acquisition to generate an initial cell image sequence; an automatic digital focusing algorithm is applied to the initial cell image sequence, and a cell image frame set with the optimal focal plane is screened out; inputting the cell image frame set into a preset PA-YOLO improved model for multi-dimensional extraction and fusion, and generating a multi-scale cell characteristic spectrum; carrying out refined feature learning and cell target positioning and classification on the multi-scale cell feature spectrum, and outputting a cell detection result; and carrying out validity verification on the cell detection result, and carrying out comparative analysis in combination with an imaging flow cytometry system to generate a cell detection report. According to the method, the imaging quality and the detection accuracy of cell images with different depths can be remarkably improved.

The invention provides a plate edge sealing quality detection method and system based on machine vision, and the method comprises the steps: obtaining image data streams continuously collected in a plate edge sealing processing process, carrying out the light intensity change feature extraction of the image data streams, and obtaining a time sequence light variable feature matrix and a space light variable gradient map of an edge sealing region in an edge sealing image frame sequence; carrying out relevance enhancement on the time sequence optical variation characteristic matrix and the spatial optical variation gradient map through a preset characteristic enhancement model, and generating an edge sealing quality characteristic map with a space-time constraint relation; performing defect mode identification based on the edge sealing quality characteristic spectrum to obtain defect types existing in the edge sealing area of the plate and position distribution characteristics of the defects in the edge sealing image frame sequence; and generating a quality optimization instruction containing a parameter adjustment instruction according to the defect type and the position distribution characteristic, and sending the quality optimization instruction to the plate edge sealing control equipment. According to the invention, the overall precision and stability of plate edge sealing quality detection can be improved.

The invention belongs to the field of image processing, and provides a gynecological tumor image processing method and system based on AI multi-modal image analysis, and the method comprises the steps: 1, obtaining an original image of a patient, and obtaining a structure mask and an image frame sequence after period alignment and structure normalization based on the original image; step 2, obtaining a focus mask sequence after structure limitation based on the image frame sequence; step 3, respectively acquiring a modal structure semantic tensor of each image in the image frame sequence, and acquiring a fused semantic feature tensor based on the modal structure semantic tensor; 4, obtaining a final focus mask based on the fused semantic feature tensor and the structure mask; and step 5, obtaining a response visualization graph based on the focus mask. The method is clear in technical structure, coherent in task chain and independent in model interface, has real deployment and continuous evolution capabilities, and is particularly suitable for gynecological image AI auxiliary system scenes under periodic driving.

The present invention discloses an artificial intelligence-based (AI-based) system and method for generating optimised operation planning and scheduling output. The AI-based system obtains at least one of: one or more data explanation videos, one or more process understanding videos, and unconstrained operational planning data, along with one or more prompts as an input. The AI-based system extracts one or more informative image frames and audio data, to train the one or more AI models and generate a planning standard operating procedure (SOP). The AI-based system processes the planning SOP, the constrained operational planning data, and the one or more prompts to generate the optimised operation planning and scheduling output based on an optimised function with a continuous feedback loop in response to at least one of: the one or more prompts, updated planning SOP, and real-time changes in the constrained operational planning data.

The embodiment of the invention provides a multi-camera video fusion method and system for a robot with a body and a storage medium, and belongs to the field of image processing. The method comprises the following steps: performing time and space alignment on images based on a vision and inertia alignment model to generate a unified aligned image sequence; extracting multi-scale image features based on the uniformly aligned image sequence, and constructing a cross-view residual image for guiding attention fusion operation to generate a fusion image; performing privacy area identification on the fused image, and performing shielding processing on a privacy area to obtain a privacy protection image; and performing semantic compression on the privacy protection image, adjusting an image frame scheduling sequence according to network link state information, and outputting a video signal for controlling a decision. The method is oriented to whole-process optimization of space-time alignment, cross-view fusion and privacy protection processing in the multi-shot image acquisition process of the robot with the body, and video signals for control are output in a self-adaptive mode based on the link state.

The invention discloses a monocular video scene dynamic three-dimensional reconstruction method based on optical flow, and relates to the technical field of scene reconstruction. Calculating an optical flow of each pixel in each frame of image in the monocular video, and determining a dynamic region mask of the image; according to the dynamic region mask of each frame of image, determining a plurality of dynamic object instances with consistent time and space; performing four-dimensional Gaussian sputtering conversion on each frame of image to obtain four-dimensional Gaussian distribution representation; for any one dynamic object instance in any one frame of image, acquiring other images containing the dynamic object instance in different image frames, and according to the coordinates of the Gaussian point clouds of the image and other images, generating a visual angle point cloud, which is not observed in the image, of the object instance; and according to color information of each frame of Gaussian point cloud in the four-dimensional Gaussian distribution representation, performing color rendering on each frame of Gaussian point cloud generating the visual angle point cloud to obtain a reconstructed scene. The method can accurately realize scene reconstruction.

The invention discloses a control method of a video monitoring system, which relates to the technical field of video monitoring, and comprises the following steps of: acquiring continuous image frames through the video monitoring system, extracting brightness channels, edge structures, direction gradients and contrast changes of images, constructing a reflective perception vector group, and calculating an included angle change trend by combining a target motion direction vector, determining whether a reflection offset condition consistent with the target direction appears in a picture in a camera attitude control process; after it is determined that the reflection offset condition consistent with the target direction appears in the picture, the inter-frame change tensor of the target area and the reflection area is extracted, and a time sequence track consistency matrix is constructed; according to the invention, the problem of wrong adjustment of the camera caused by misjudgment of light reflection in video monitoring is solved, attitude regulation and control based on image displacement abnormal mode recognition are realized, and the tracking stability and the monitoring accuracy are improved.

The invention discloses a video training data generation method based on multi-modal semantic alignment, and relates to the technical field of audio and video processing. The method specifically comprises the following steps: (1) carrying out multi-modal time alignment on audio, image frames and text information in a video, and establishing a cross-modal time sequence mapping relation; (2) semantic enhancement processing is carried out based on the time alignment result, and the identification accuracy of the terminology is improved; (3) dynamically grading the training samples according to the semantic density and the confidence coefficient; and (4) outputting the graded structured training data to adapt to different training stages. The method aims at improving the quality of training data from a video data source and avoiding occurrence of a large amount of redundant data and missing of key nodes.

The invention provides an abnormity early warning security system and method based on cross-modal semantic retrieval, and relates to the technical field of public security, and the system comprises a video collection and frame sampling module which is used for extracting key frame images from a real-time monitoring video stream according to a preset frame interval and storing the key frame images to an object storage system; the target detection module adopts a YOLO model to execute instance-level target detection on the extraction frame, and generates a structured detection result containing a target position, a category and confidence; the semantic vector storage and structured warehousing module packages the standardized metadata of the image frame and the semantic vector generated by the CLIP into structured data, and stores the structured data into a high-performance vector database; and the semantic retrieval and reverse query module receives a natural language query instruction to generate a semantic vector, and realizes cross-modal retrieval of historical monitoring images through vector similarity matching. According to the invention, a set of exception security system with real-time perception capability, semantic understanding capability and cross-modal retrieval capability is constructed.

The invention relates to the technical field of defect detection, in particular to a dynamic defect real-time detection system based on deep learning, and the system comprises an image sequence preprocessing module which is used for defining a three-dimensional space-time neighborhood for pixel data of each frame based on an input dynamic image frame and adjusting the neighborhood block form according to the local intensity change direction of the pixel data, and obtaining a space-time filtering frame sequence, analyzing the space-time filtering frame sequence, converting pixel data in a logarithm domain, and separating illumination components by iteratively updating a local pixel intensity estimation value. According to the method, the three-dimensional space-time neighborhood is defined for the input dynamic image frame, the neighborhood block form is adjusted according to the local intensity change direction, the weighted average of the neighborhood pixel data can retain the dynamic defect characteristics and suppress the background noise influence, and the local pixel intensity estimation value is updated through logarithm domain conversion and iteration. And illumination variation factors are reliably separated, so that the robustness and adaptability of the image are enhanced.

A computer implemented method for enhancing underwater imagery is disclosed. A sequence of raw image frames including a current raw image frame is received. The raw image frames are processed with an Artificial Intelligence (AI) image enhancement model to provide enhanced image frames including a current enhanced image frame. Image quality scores are determined for the enhanced image frames. Based on the image quality scores, one of the enhanced image frames is set as an enhanced image template. Color characteristics of the current enhanced image frame are adjusted using a color transfer function for applying color characteristics of the enhanced image template to those of the current enhanced image frame. Unlocking insights from Geo-Data, the present invention further relates to improvements in sustainability and environmental developments: together we create a safe and liveable world.

The present invention provides an automatic focusing method, an electronic device, and a readable storage medium. The automatic focusing method comprises: using a target detection model to detect a target object in an image frame acquired at an initial focal length by an optical imaging device to be focused, so as to acquire a target object detection result; on the basis of the target object detection result, determining whether a target object is present in the image frame; if yes, determining an actual object distance on the basis of the target object detection result and the initial focal length, and on the basis of the actual object distance and a mapping relationship between the object distance and an optimal imaging focal length, determining the optimal imaging focal length; and if not, using a preset search algorithm to search for a focal length until an image having the highest definition value is found, and using a focal length corresponding to the image having the highest definition value as the optimal imaging focal length. The present invention primarily employs a deep learning-based automatic focusing method, supplemented by an image definition evaluation method. Compared with traditional passive focusing methods, the present invention greatly improves the focusing efficiency. Compared with traditional active focusing methods, the present invention eliminates a need for adding an additional optical ranging component, ensuring that the imaging device has a simple structure and a low cost.

A system includes a processor circuit that receives intraluminal images obtained by an intraluminal imaging device during movement through a patient's body lumen. The processor circuit outputs, to a display, a visual representation of user guidance in response to the processor circuit identifying, among the intraluminal images, a candidate intraluminal image. The user guidance includes stopping the movement and instructing the patient to initiate deep breathing. The processor circuit receives additional intraluminal images obtained by the intraluminal imaging device while the movement is stopped and the patient is deep breathing. The processor circuit determines if a shape and / or size of the body lumen changes in the additional intraluminal images. The processor circuit accepts or rejects the candidate intraluminal image based on if the shape and / or size of the body lumen changes. The processor circuit outputs, to the display, a visual representation corresponding to accepting or rejecting the candidate intraluminal image.

The invention provides a multi-mode remote sensing target tracking and positioning and intention discrimination method and device. The method comprises the following steps: acquiring a plurality of visible light image frames and a plurality of infrared light image frames, and carrying out frame alignment operation on each visible light image frame and each infrared light image frame to obtain a plurality of groups of effective image frame pairs; for each group of effective image frame pairs, determining tracking identification information of each detection object in the effective image frame pairs based on the effective image frame pairs and a pre-trained multi-modal detection tracking model; for each detection object, determining longitude and latitude tracks of the detection object based on the tracking identification information and a back projection mapping function; and determining the behavior intention of each detection object based on a behavior recognition model and the longitude and latitude tracks of each detection object. The accuracy of target tracking and behavior intention recognition in the remote sensing video can be improved.

The invention relates to the technical field of computers, and relates to a rendering model training method and device, an illumination rendering method and device, a computer program product and electronic equipment. The training method comprises the following steps: extracting inherent attribute information and global light and shadow information of a to-be-rendered object from an image frame sample based on a teacher model; performing feature decoding on the Gaussian primitives by using an initial student model to obtain a basic physical attribute, and determining a first loss according to the basic physical attribute and the inherent attribute information, the initial student model comprising a plurality of Gaussian primitives attached to a deformable grid; interpolating light and shadow data of the probe model through the initial student model to obtain current light and shadow information, constructing second loss according to the current light and shadow information and global light and shadow information, and arranging the probe model on the surface of the deformable grid; and adjusting parameters in the initial student model according to the first loss and the second loss, and adjusting shadow data of the probe model to obtain a target student model and a target probe model.

The invention belongs to the technical field of abnormal behavior person recognition, and particularly relates to an abnormal behavior person recognition method based on multi-source monitoring image integration. The method comprises the steps of obtaining original video data of a plurality of cameras in a target area; judging whether a person completely appears or partially disappears through an attitude estimation and semantic segmentation model, carrying out inter-frame sampling by taking the judgment as a starting point and a stopping point, and retaining time-space information; preprocessing the image frames, and extracting static posture and dynamic behavior characteristics; fusing dynamic behaviors, appearance and position information to realize cross-camera personnel identity association and construct a behavior track sequence; and matching the trajectory with a preset template, and calculating a deviation score in combination with time consistency, position path similarity, an action matching degree and an abnormal fragment confidence aggregation value to recognize abnormal personnel. The method breaks through the limitation of a single visual angle, improves the low-illumination recognition precision, solves the problem of cross-visual-angle identity breakage, and improves the recognition accuracy and traceability of abnormal behaviors.